Boundary Character Research Articles

Scene-Adaptive 3D Semantic Segmentation Based on Multi-Level Boundary-Semantic-Enhancement for Intelligent Vehicles

3D semantic segmentation is a key technology of scene understanding in the self-driving field, which remains challenging problems. Recent 3D segmentation methods have achieved competitive results in indoor or typical urban traffic scenes. However, in complex and changeable scenarios where structured features are sparse and irregular, few of these methods could achieve well segmentation results, especially causing blurry and inaccurate boundary distinctions between inter-class objects, drivable areas, and backgrounds. In order to fully harvest boundary information and accurately distinguish the category of points on road and object boundaries in real-time, we present an efficient multi-level boundary-semantic-enhanced model for LiDAR semantic segmentation, which comprehensively discover boundary features in three aspects: first, boundary channels are extracted directly from LiDAR range images as the inputs of boundary-branch; second, the boundary attention module is designed to deeply fuse boundary information into the main segmentation branch; third, a modified discriminator is utilized to raise the perception of boundary information by minimizing the gap between the predicted and true boundaries. Besides, we add a semantic-enhanced module using the similar discriminator to optimize semantic segmentation results in the output end. Quantitative and qualitative evaluations are performed on both structured and unstructured real-world datasets including urban dataset SemanticKITTI, off-road dataset Rellis3D and our unstructured test set. The experimental results validate the effectiveness of the proposed methodology in improving efficiency, accuracy and scene-adaptivity.

Context-Aware Proposal-Boundary Network With Structural Consistency for Audiovisual Event Localization.

Audiovisual event localization aims to localize the event that is both visible and audible in a video. Previous works focus on segment-level audio and visual feature sequence encoding and neglect the event proposals and boundaries, which are crucial for this task. The event proposal features provide event internal consistency between several consecutive segments constructing one proposal, while the event boundary features offer event boundary consistency to make segments located at boundaries be aware of the event occurrence. In this article, we explore the proposal-level feature encoding and propose a novel context-aware proposal-boundary (CAPB) network to address audiovisual event localization. In particular, we design a local-global context encoder (LGCE) to aggregate local-global temporal context information for visual sequence, audio sequence, event proposals, and event boundaries, respectively. The local context from temporally adjacent segments or proposals contributes to event discrimination, while the global context from the entire video provides semantic guidance of temporal relationship. Furthermore, we enhance the structural consistency between segments by exploiting the above-encoded proposal and boundary representations. CAPB leverages the context information and structural consistency to obtain context-aware event-consistent cross-modal representation for accurate event localization. Extensive experiments conducted on the audiovisual event (AVE) dataset show that our approach outperforms the state-of-the-art methods by clear margins in both supervised event localization and cross-modality localization.

BFG&MSF-Net: Boundary Feature Guidance and Multi-Scale Fusion Network for Thyroid Nodule Segmentation

BFG&MSF-Net: Boundary Feature Guidance and Multi-Scale Fusion Network for Thyroid Nodule Segmentation

Dental panoramic X-ray image segmentation for multi-feature coordinate position learning.

To achieve an accurate assessment of orthodontic and restorative treatments, tooth segmentation of dental panoramic X-ray images is a critical preliminary step, however, dental panoramic X-ray images suffer from poorly defined interdental boundaries and low root-to-alveolar bone contrast, which pose significant challenges to tooth segmentation. In this article, we propose a multi-feature coordinate position learning-based tooth image segmentation method for tooth segmentation. For better analysis, the input image is randomly flipped horizontally and vertically to enhance the data. Our method extracts multi-scale tooth features from the designed residual omni-dimensional dynamic convolution and the designed two-stream coordinate attention module can further complement the tooth boundary features, and finally the two features are fused to enhance the local details of the features and global contextual information, which achieves the enrichment and optimization of the feature information. The publicly available adult dental datasets Archive and Dataset and Code were used in the study. The experimental results were 87.96% and 92.04% for IoU, 97.79% and 97.32% for ACC, and 86.42% and 95.64% for Dice. The experimental results show that the proposed network can be used to assist doctors in quickly viewing tooth positions, and we also validate the effectiveness of the proposed two modules in fusing features.

Influence of Spheroidized Cementite on Ferritic Matrix Boundary Characteristics and Mechanical Behavior in Commercial Carbon Steels

Influence of Spheroidized Cementite on Ferritic Matrix Boundary Characteristics and Mechanical Behavior in Commercial Carbon Steels

AI-Powered Segmentation of Invasive Carcinoma Regions in Breast Cancer Immunohistochemical Whole-Slide Images.

The automation of quantitative evaluation for breast immunohistochemistry (IHC) plays a crucial role in reducing the workload of pathologists and enhancing the objectivity of diagnoses. However, current methods face challenges in achieving fully automated immunohistochemistry quantification due to the complexity of segmenting the tumor area into distinct ductal carcinoma in situ (DCIS) and invasive carcinoma (IC) regions. Moreover, the quantitative analysis of immunohistochemistry requires a specific focus on invasive carcinoma regions. In this study, we propose an innovative approach to automatically identify invasive carcinoma regions in breast cancer immunohistochemistry whole-slide images (WSIs). Our method leverages a neural network that combines multi-scale morphological features with boundary features, enabling precise segmentation of invasive carcinoma regions without the need for additional H&E and P63 staining slides. In addition, we introduced an advanced semi-supervised learning algorithm, allowing efficient training of the model using unlabeled data. To evaluate the effectiveness of our approach, we constructed a dataset consisting of 618 IHC-stained WSIs from 170 cases, including four types of staining (ER, PR, HER2, and Ki-67). Notably, the model demonstrated an impressive intersection over union (IoU) score exceeding 80% on the test set. Furthermore, to ascertain the practical utility of our model in IHC quantitative evaluation, we constructed a fully automated Ki-67 scoring system based on the model's predictions. Comparative experiments convincingly demonstrated that our system exhibited high consistency with the scores given by experienced pathologists. Our developed model excels in accurately distinguishing between DCIS and invasive carcinoma regions in breast cancer immunohistochemistry WSIs. This method paves the way for a clinically available, fully automated immunohistochemistry quantitative scoring system.

Land use types at the boundaries between settlements and open landscape in suburbanised settlements on the example of the Czech Republic from the perspective of the potential for planting tall vegetation

Background and aimsSettlement boundaries in suburbanised areas represent a specific environment connecting the settlements with the surrounding open landscape. Traditionally, tall vegetation (such as orchards planted in the backyards) used to form this boundary, providing a gradual transition as well as a wide range of ecosystem services. With suburbanisation, however, there appears to be a trend towards sharper boundaries between the open landscape and the settlement. The degree of the effect of suburbanisation on the boundary has, however, not been thoroughly explored yet. In this paper, the current character of such boundaries is evaluated from the perspective of land use and potential for tall vegetation. In addition, possible impacts of such changes are discussed, and measures for preventing these impacts are proposed. MethodsOn 50 suburbanised settlements in the Czech Republic, the land use types, water permeability, and suitability for the growth of tall vegetation within an 80 m belt enveloping the boundary between the settlement and open landscape were analysed using ArcGIS tools and artificial intelligence algorithms. ResultsThe dominant land use types were Residential on the inner side of the margins and Farmland on the outside of the margins, with a few meters of the transitional zone. These homogeneous land use types represented approx. 70 % of land use types at a distance of 10 m or more from the boundary. The representation of water-absorbing areas on the residential side of the boundary declined from 80 % at the settlement boundary to approx. 55 % at 40 m inside the settlement; this drop was even more pronounced for areas suitable for tall vegetation (from 90 % at 20 m outside of the boundary to 70 % at the boundary and 35 % at 40 m within the settlement). However, the potential for planting tall vegetation at the outer margins is underutilised. ConclusionsThe dominance of farmland in the immediate vicinity of the boundary between suburbanised settlements and open landscape and the underutilisation of the potential for planting tall vegetation on the outer margins deprive the settlements of ecosystem services of such ecotone and lead to the loss of habitats for wild animal and plant species.

Characteristics of limited flow and soil water infiltration boundary of a subsurface drip irrigation emitter in silty loam soil

The accurate estimation of the infiltration boundary of a buried point source is required in the hydraulic design of a subsurface drip irrigation (SDI) system, as well as in the numerical simulation of soil water movement. In this study, an experiment was conducted to measure the variation in emitter flow rate and soil back pressure in silty loam soil. The infiltration cavity was observed, and the radius was estimated by matching the measured emitter flow rate and soil back pressure using HYDRUS-2D simulations. The relationship between the cavity radius, emitter flow rate, and soil back pressure, as affected by the soil bulk density, working pressure, and nominal emitter flow rate, are discussed. The results indicate that the infiltration cavity formed rapidly during irrigation with an irregular shape. The surface area increased as nominal emitter flow rate increased and soil bulk density increased. The variation of flow rate as a function of time had no necessary relationship with that of soil back pressure, due to the formation of the cavity. When the infiltration process became stable, higher soil bulk density resulted in increase in soil back pressure and decrease in emitter flow rate. However, the effects of working pressure and nominal emitter flow rate on soil back pressure were unclear. The emitter flow rate and back pressure, solved by an existing analytical model using estimated radius, demonstrated satisfactory agreement with the measured data, with the minimum root-mean-square error (RMSE), compared with those using a constant radius. When the infiltration boundary was taken as a constant head, the soil back pressure and cavity both significantly affected the simulated soil wetting patterns. The effect of cavity radius on the wetting front could be neglected for the constant flux boundary.

High-Precision Carton Detection Based on Adaptive Image Augmentation for Unmanned Cargo Handling Tasks.

Unattended intelligent cargo handling is an important means to improve the efficiency and safety of port cargo trans-shipment, where high-precision carton detection is an unquestioned prerequisite. Therefore, this paper introduces an adaptive image augmentation method for high-precision carton detection. First, the imaging parameters of the images are clustered into various scenarios, and the imaging parameters and perspectives are adaptively adjusted to achieve the automatic augmenting and balancing of the carton dataset in each scenario, which reduces the interference of the scenarios on the carton detection precision. Then, the carton boundary features are extracted and stochastically sampled to synthesize new images, thus enhancing the detection performance of the trained model for dense cargo boundaries. Moreover, the weight function of the hyperparameters of the trained model is constructed to achieve their preferential crossover during genetic evolution to ensure the training efficiency of the augmented dataset. Finally, an intelligent cargo handling platform is developed and field experiments are conducted. The outcomes of the experiments reveal that the method attains a detection precision of 0.828. This technique significantly enhances the detection precision by 18.1% and 4.4% when compared to the baseline and other methods, which provides a reliable guarantee for intelligent cargo handling processes.

Magnetic effects on surface waves in a rotating non-homogeneous half-space with grooved and impedance boundary characteristics

Investigation on the Mathematical modeling of waves in a rotating grooved and impedance boundary of a non-homogeneous fibre-reinforced solid half‐space under the influence of magnetic field and mechanical force is envisaged. We derived analytically, the dynamical equations for the rotating grooved and impedance boundary of the non-homogeneous fibre-reinforced solid under the influence of magnetic fields and mechanical force. Harmonic solution method of wave analysis is utilized. This is such that the component of displacements and stresses are developed and studied after employing dimensionless parameters in the equations of motion. Numerical computations are presented in graphical form by using Mathematica Software for a particular chosen material. We observed that the combined grooved, magnetic fields, impedance boundary etc. physical parameters, have remarkable effects on the material. A decrease in horizontal impedance yielded maximum amplitudes of displacements and stresses of the waves on the fibre-reinforced medium. The mechanical force and rotation of the medium induced increased behaviors to the amplitudes of displacement and stress components of the wave on the solid medium. Thus, this work should be of great importance in studies involving seismology and seismic Mechatronics solution for stress-wave generation in non-homogeneous materials.

Effect of austenitizing temperature on martensitic transformation in SA508Gr.4N steel

SA508Gr.4 N steel is commonly used in nuclear pressure vessels. The current study discloses the impact of austenitizing temperature on its martensitic transformation. Various austenitizing temperatures were employed to examine the martensitic transformation at different experimental conditions. The characteristics of grain boundaries, microstructure, transformation kinetics, and crystallography of the martensitic phase following the austenitizing process and martensitic transformation were analyzed. Austenitizing temperatures had minimal effects on the critical temperature of the austenitizing phase transition. However, an increase in austenitizing temperature resulted in larger grain sizes. The phase composition primarily consisted of lath martensite, accompanied by a small amount of residual austenite (RA). As the austenitizing temperature increased, the temperature of martensite-start temperature (Ms) initially decreased and then increased. On the other hand, the temperature of martensite-finish (Mf) showed no significant sensitivity to changes in the austenitizing temperature. Moreover, the average size of the lath martensite structure was increased, and there was an increased tendency for variant selection as the austenitizing temperature increased, and the combination of specific orientation relationships appeared. This study is very valuable for revealing the microstructure evolution at different temperatures.

Cracking mechanism of GH5188 alloy during laser powder bed fusion additive manufacturing

GH5188 cobalt-based superalloy components fabricated using laser powder bed fusion (LPBF) additive manufacturing technique possess promising application prospects in aviation industry, but high cracking susceptibility of the alloy remains an important concern. In this paper, cracking mechanism of the LPBFed GH5188 alloy was investigated by analyzing microstructure, fracture surfaces, composition distribution and grain boundary characteristics of the prepared sample. It was found that cracks consistently propagate intergranular at grain boundaries with high misorientation angle. The cracks were confirmed to be solidification cracks, due to the existence of fracture surface with dendritic morphology, as well as the absence of eutectic structure, carbide and precipitated phase. Lanthanum oxide particles were observed in the as-built alloy, which may hamper feeding of molten material at interdendritic region, promoting tearing of liquid films. Hence, it could be suggested that low O and La contents help in avoiding crack formation. This work could provide guidance for fabrication of crack-free LPBFed GH5188 alloy components.

COVID-19 infection analysis framework using novel boosted CNNs and radiological images

COVID-19, a novel pathogen that emerged in late 2019, has the potential to cause pneumonia with unique variants upon infection. Hence, the development of efficient diagnostic systems is crucial in accurately identifying infected patients and effectively mitigating the spread of the disease. However, the system poses several challenges because of the limited availability of labeled data, distortion, and complexity in image representation, as well as variations in contrast and texture. Therefore, a novel two-phase analysis framework has been developed to scrutinize the subtle irregularities associated with COVID-19 contamination. A new Convolutional Neural Network-based STM-BRNet is developed, which integrates the Split-Transform-Merge (STM) block and Feature map enrichment (FME) techniques in the first phase. The STM block captures boundary and regional-specific features essential for detecting COVID-19 infectious CT slices. Additionally, by incorporating the FME and Transfer Learning (TL) concept into the STM blocks, multiple enhanced channels are generated to effectively capture minute variations in illumination and texture specific to COVID-19-infected images. Additionally, residual multipath learning is used to improve the learning capacity of STM-BRNet and progressively increase the feature representation by boosting at a high level through TL. In the second phase of the analysis, the COVID-19 CT scans are processed using the newly developed SA-CB-BRSeg segmentation CNN to accurately delineate infection in the images. The SA-CB-BRSeg method utilizes a unique approach that combines smooth and heterogeneous processes in both the encoder and decoder. These operations are structured to effectively capture COVID-19 patterns, including region-homogenous, texture variation, and border. By incorporating these techniques, the SA-CB-BRSeg method demonstrates its ability to accurately analyze and segment COVID-19 related data. Furthermore, the SA-CB-BRSeg model incorporates the novel concept of CB in the decoder, where additional channels are combined using TL to enhance the learning of low contrast regions. The developed STM-BRNet and SA-CB-BRSeg models achieve impressive results, with an accuracy of 98.01%, recall of 98.12%, F-score of 98.11%, Dice Similarity of 96.396%, and IOU of 98.85%. The proposed framework will alleviate the workload and enhance the radiologist's decision-making capacity in identifying the infected region of COVID-19 and evaluating the severity stages of the disease.

Epidermis lesion detection via optimized distributed capsule neural network

Skin cancer, encompassing various forms such as melanoma, basal cell carcinoma, and others, remains a significant global health concern, often proving fatal if not diagnosed and treated in its early stages. The challenge of accurately diagnosing skin cancer, particularly melanoma, persists even for experienced dermatologists due to the intricate and unpredictable nature of its symptoms. To address the need for more accurate and efficient skin cancer detection, a novel Golden Hawk Optimization-based Distributed Capsule Neural Network (GHO-DCaNN) is proposed. This novel technique leverages advanced computational methods to improve the reliability and precision of skin cancer diagnosis. An optimized clustering-based segmentation approach is introduced, integrating the innovative Sewer Shad Fly Optimization (SSFO), which combines elements of both mayfly and moth flame optimization. This integration enhances the accuracy of lesion boundary delineation and feature extraction. The core of the innovation lies in the optimized distributed capsule neural network, which is trained using the Hybrid GHO. This optimizer, inspired by the behaviors of the golden eagle and fire hawk, ensures the effectiveness of epidermis lesion detection, pushing the boundaries of skin cancer diagnosis methods. The achievements based on the metrics, like specificity, sensitivity, and accuracy show 97.53%, 99.05%, and 98.83% for 90% of training and 97.83%, 99.50%, and 99.06% for k-fold of 10, respectively.

Deciphering the effect of grain boundary characteristics on fracture toughness of silicon nitride ceramics through a CNN regression model

Fracture toughness of silicon nitride (Si3N4) ceramics with different grain boundary characteristics was determined from their microstructural images via a convolutional neural network (CNN) model. For this purpose, the CNN model was trained using Si3N4 ceramics with sintering additives of Y2O3 and MgO, and then the fracture toughness for those with various lanthanoid oxides and MgO was determined from the microstructural images through the trained model. Herein, the difference between the determined and measured values indicates the effect of the grain boundary characteristics because they little appear in the microstructures. The measured and AI-determined fracture toughness showed that the large ionic radius of Sm2O3 enhanced the fracture toughness of the Si3N4 ceramics sintered at 1850 °C for 24 h. The trained model successfully determined fracture toughness values that closely matched the measured ones from the microstructural images, even for samples with pores and different grain boundary characteristics, except for the Sm2O3 sample sintered for 24 h.

Impact of grain-dependent boron uptake on the nano-electrical and local optical properties of polycrystalline boron doped CVD diamond

Boron-doped diamond (BDD) films grown by chemical vapor deposition (CVD) exhibit unique electrical and optical properties owing to the non-uniform uptake of boron dopants across grains. This study utilizes scanning probe microscopy and confocal micro- spectroscopy techniques to elucidate the influence of grain-dependent boron incorporation on the nano-electrical and local optical characteristics of polycrystalline BDD. The CVD- grown BDD film contained crystallites up to tens of microns, while the surface comprised 200…800 nm grains. Scanning spreading resistance microscopy (SSRM) revealed significant nanoscale resistance variations among individual grains, attributable to differential boron distributions. No distinct grain boundary features were discernible in SSRM data, likely due to the high boron doping of ~ 3·10 19 cm –3 . SSRM of the Au surface of a BDD/Ti/Pd/Au contact indicated a comparable granular morphology but three orders lower resistance. A network of more resistive grain boundaries was evident, modulated by underlying BDD grain clusters. Photoluminescence spectroscopy showed characteristic bands of nitrogen-vacancy centers and donor-acceptor pairs. Confocal Raman and photoluminescence mapping elucidated substantial spatial heterogeneity in micrometer- scale grains regarding crystal quality, boron and nitrogen concentrations, related to preferential incorporation. The observed peculiarities in BDD’s structural and nano- electrical characteristics stem from inherent growth inhomogeneities and grain-dependent boron uptake influenced by defects and strain fields modifying local chemical potentials. This multifaceted nanoscale examination provides critical insights into optimizing electrical and optical properties of BDD films by controlling synthesis conditions and minimizing defects for tailored performance in electronic, electrochemical, and quantum applications.

A Novel Building Extraction Network via Multi-Scale Foreground Modeling and Gated Boundary Refinement

Deep learning-based methods for building extraction from remote sensing images have been widely applied in fields such as land management and urban planning. However, extracting buildings from remote sensing images commonly faces challenges due to specific shooting angles. First, there exists a foreground–background imbalance issue, and the model excessively learns features unrelated to buildings, resulting in performance degradation and propagative interference. Second, buildings have complex boundary information, while conventional network architectures fail to capture fine boundaries. In this paper, we designed a multi-task U-shaped network (BFL-Net) to solve these problems. This network enhances the expression of the foreground and boundary features in the prediction results through foreground learning and boundary refinement, respectively. Specifically, the Foreground Mining Module (FMM) utilizes the relationship between buildings and multi-scale scene spaces to explicitly model, extract, and learn foreground features, which can enhance foreground and related contextual features. The Dense Dilated Convolutional Residual Block (DDCResBlock) and the Dual Gate Boundary Refinement Module (DGBRM) individually process the diverted regular stream and boundary stream. The former can effectively expand the receptive field, and the latter utilizes spatial and channel gates to activate boundary features in low-level feature maps, helping the network refine boundaries. The predictions of the network for the building, foreground, and boundary are respectively supervised by ground truth. The experimental results on the WHU Building Aerial Imagery and Massachusetts Buildings Datasets show that the IoU scores of BFL-Net are 91.37% and 74.50%, respectively, surpassing state-of-the-art models.

Automatic Plastic Greenhouse Extraction from Gaofen-2 Satellite Images with Fully Convolution Networks and Image Enhanced Index

Plastic greenhouses (PGs) play a vital role in modern agricultural development by providing a controlled environment for the cultivation of food crops. Their widespread adoption has the potential to revolutionize agriculture and impact the local environment. Accurate mapping and estimation of PG coverage are critical for strategic planning in agriculture. However, the challenge lies in the extraction of small and densely distributed PGs; this is often compounded by issues like irrelevant and redundant features and spectral confusion in high-resolution remote-sensing imagery, such as Gaofen-2 data. This paper proposes an innovative approach that combines the power of a full convolutional network (FC-DenseNet103) with an image enhancement index. The image enhancement index effectively accentuates the boundary features of PGs in Gaofen-2 satellite images, enhancing the unique spectral characteristics of PGs. FC-DenseNet103, known for its robust feature propagation and extensive feature reuse, complements this by addressing challenges related to feature fusion and misclassification at the boundaries of PGs and adjacent features. The results demonstrate the effectiveness of this approach. By incorporating the image enhancement index into the DenseNet103 model, the proposed method successfully eliminates issues related to the fusion and misclassification of PG boundaries and adjacent features. The proposed method, known as DenseNet103 (Index), excels in extracting the integrity of PGs, especially in cases involving small and densely packed plastic sheds. Moreover, it holds the potential for large-scale digital mapping of PG coverage. In conclusion, the proposed method providing a practical and versatile tool for a wide range of applications related to the monitoring and evaluation of PGs, which can help to improve the precision of agricultural management and quantitative environmental assessment.

A similarity approach to the turbulent near-wake of a long slender cylinder with a sharp trailing edge at zero pressure gradient

A high Reynolds number wake flow developing under zero pressure gradient from a long slender axisymmetric cylinder with sharp trail ending is investigated. The main focus is the flow domain immediately behind the trailing edge, where the fully developed upstream turbulent boundary layers separated by the body, unite under no body constraints and the boundary layer identity and characteristics are gradually lost. Similarity solutions for the streamwise mean velocity and centreline velocity are obtained in which the region exhibits the log law of the fully developed boundary layer. A critical assessment of inner near wake characteristic length is done.

Boundary-Aware Network With Topological Consistency Constraint for Optic Chiasm Segmentation

Optic chiasm is a structure which is easily compressed by the tumors leading to different degrees of visual field defect and visual disturbance. When the optic chiasm is compressed, segmentation of the optic chiasm from MRI images is helpful for prognosis prediction and radiotherapy planning. However, due to the ambiguity of the optic chiasm boundary and the neglect of the anatomical structure consistency, the performance of the existing methods is limited. In this work, a Boundary-Aware Network (BANet) with topological consistency constraint is proposed for automated segmentation of optic chiasm. BANet constrained by topology loss leverages the complementary information between boundary feature and segmentation feature to effectively improve segmentation performance and topological consistency. To evaluate the effectiveness of the proposed method, a real-world specialized optic chiasm segmentation dataset is constructed. The experimental results demonstrate that the proposed method achieves higher segmentation accuracy compared with the state-of-the-art method.